Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Series
    -0.07
     última
    -0.07
     announcements
    -0.07
     devam
    -0.06
     Raq
    -0.06
    cross
    -0.06
     costumes
    -0.06
     shows
    -0.06
    目的
    -0.06
     evaluating
    -0.06
    POSITIVE LOGITS
    ціональ
    0.06
     Fairy
    0.06
    RowAnimation
    0.06
    FAILURE
    0.06
    μισ
    0.06
     PRES
    0.06
    _VER
    0.06
     xúc
    0.06
     encuent
    0.06
     eksik
    0.06
    Act Density 0.006%

    No Known Activations